Skip to content
fedi.software

jamba-1.5-mini in fedi-index

The score in every slice, what it is made of, value, local run and history.

fedi-index · General

D 1,184 ±4

Percentile 22 · #229 · provisional

People prefer / Solves tasks

1,183 / —

Human votes vs benchmarks, Elo-eq

Value

-160

$0.25 per 1M tokens, median of 2 providers · vendor $0.25

On your hardware

Closed weights: cloud only.

Score decomposition

D General 1,184 [1,180–1,189] Percentile 22 · #229 · components: 6 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/overall 1,187 ±3.65 1,187 ±4 27.7% 2026-10-02 —
LMArena text/hard_prompts 1,167 ±6.00 1,184 ±5 26.0% 2026-10-02 —
LMArena text/instruction_following 1,148 ±5.35 1,174 ±5 13.2% 2026-10-02 —
LMArena text/expert 1,136 ±16 1,178 ±13 8.5% 2026-10-02 —
LMArena text/multi_turn 1,157 ±7.43 1,178 ±7 6.1% 2026-10-02 —
LMArena text/longer_query 1,157 ±8.85 1,173 ±8 5.6% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Coding 1,186 [1,174–1,198] Percentile 20 · #222 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/coding 1,178 ±7.73 1,184 ±7 88.8% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Math 1,168 [1,155–1,182] Percentile 19 · #207 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/math 1,160 ±8.15 1,163 ±8 86.3% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Writing 1,184 [1,173–1,195] Percentile 23 · #207 · components: 2 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/creative_writing 1,164 ±7.93 1,188 ±8 61.9% 2026-10-02 —
LMArena text/longer_query 1,157 ±8.85 1,173 ±8 30.6% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Language: 繁體中文 1,167 [1,151–1,182] Percentile 13 · #195 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/chinese 1,135 ±11 1,164 ±9 92.3% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

C Language: English 1,202 [1,193–1,211] Percentile 26 · #203 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/english 1,224 ±4.58 1,202 ±5 93.6% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

D Language: Русский 1,189 [1,174–1,204] Percentile 12 · #205 · components: 1 provisional
Source Component Value Elo-eq Weight Measured Variant
LMArena text/russian 1,156 ±9.10 1,188 ±8 92.5% 2026-10-02 —

Weight is the share of the component in the score (the rest is the prior that pulls models with little data towards the population median). Methodology

History

fedi-index by month
The same in a table
Model 2026-10
jamba-1.5-mini 1,184 D

Badge

Show the model's fedi-index on your site or in a README. The badge updates itself; it links to this page.

fedi-index: jamba-1.5-mini

Data CC BY 4.0: keep the link to fedi.software.